We study how to leverage off-the-shelf visual and linguistic data to cope with out-of-vocabulary answers in visual question answering task. Existing large-scale visual datasets with annotations such as image class labels, bounding boxes and region descriptions are good sources for learning rich and diverse visual concepts. However, it is not straightforward how the visual concepts can be captured and transferred to visual question answering models due to missing link between question dependent answering models and visual data without question. We tackle this problem in two steps: 1) learning a task conditional visual classififier, which is capable of solving diverse questionspecifific visual recognition tasks, based on unsupervised task discovery and 2) transferring the task conditional visual classififier to visual question answering models. Specifically, we employ linguistic knowledge sources such asstructured lexical database (e.g. WordNet) and visual descriptions for unsupervised task discovery, and transfer a learned task conditional visual classififier as an answering unit in a visual question answering model. We empirically show that the proposed algorithm generalizes to out-ofvocabulary answers successfully using the knowledge transferred from the visual dataset.